Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

dogfood

skill · nousresearch/hermes-agentMIT licenceAudited 14 Nov 2026 · source b42117873683

★ 263,254pushed todayversion 1.0.0
✓SAFEGrade B · 89/100 · 14 Nov 2026 · b421178
263,254repo stars · whole nousresearch/hermes-agent

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit b42117873683 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Exploratory QA of web apps: find bugs, evidence, reports.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “dogfood (nousresearch/hermes-agent)”. Retrieved 14 Nov 2026. https://modelsatlas.com/skills/nousresearch/dogfood

3 skills are called “dogfood”. You are viewing nousresearch/hermes-agent.

Trust audit

Audit 0.4.1 · source read 14 Nov 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 17,406 of 18,389 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha b42117873683 · 14 Nov 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishernousresearch GitHub organizationOwner of the repository this skill is read from
  • Source foldernousresearch/hermes-agent/skills/software-development/dogfoodThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdictb42117873683A new audit runs when the source changes
  • Repository statusNot archivedPushed today
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Exploratory QA of web apps: find bugs, evidence, reports.

---
name: dogfood
description: "Exploratory QA of web apps: find bugs, evidence, reports."
version: 1.0.0
author: Teknium (teknium1), Hermes Agent
license: MIT
platforms: [linux, macos, windows]
metadata:
  hermes:
    tags: [qa, testing, browser, web, dogfood]
    related_skills: []
---

# Dogfood: Systematic Web Application QA Testing

## Overview

This skill guides you through systematic exploratory QA testing of web applications with `browser_exec`. You will navigate the application, interact with elements, capture evidence of issues, and produce a structured bug report.

## Prerequisites

- The `browser` toolset must be enabled (`browser_exec`). `browser_exec` runs Python with pre-imported helpers (`new_tab`, `goto_url`, `wait_for_load`, `page_info`, `js`, `fill_input`, `click_at_xy`, `capture_screenshot`, `cdp`); browser state persists across calls, Python variables do not.
- A target URL and testing scope from the user

## Inputs

The user provides:
1. **Target URL** — the entry point for testing
2. **Scope** — what areas/features to focus on (or "full site" for comprehensive testing)
3. **Output directory** (optional) — where to save screenshots and the report (default: `./dogfood-output`)

## Workflow

Follow this 5-phase systematic workflow:

### Phase 1: Plan

1. Create the output directory structure:
   ```
   {output_dir}/
   ├── screenshots/       # Evidence screenshots
   └── report.md          # Final report (generated in Phase 5)
   ```
2. Identify the testing scope based on user input.
3. Build a rough sitemap by planning which pages and features to test:
   - Landing/home page
   - Navigation links (header, footer, sidebar)
   - Key user flows (sign up, login, search, checkout, etc.)
   - Forms and interactive elements
   - Edge cases (empty states, error pages, 404s)

### Phase 2: Explore

Batch each step's actions into one `browser_exec` call. For each page or feature in your plan:

1. **Navigate with a console hook installed.** Register the hook on the tab before navigating so errors thrown during page load are captured too:
   ```python
   # Open page with console-error capture
   HOOK = """window.__qa_errors = [];
   const _e = console.error;
   console.error = (...a) => { window.__qa_errors.push(a.map(String).join(' ')); _e(...a); };
   addEventListener('error', e => window.__qa_errors.push('uncaught: ' + e.message));
   addEventListener('unhandledrejection', e => window.__qa_errors.push('rejection: ' + String(e.reason)));"""
   new_tab('about:blank')  # first call only: the hook binds to the current tab
   cdp('Page.addScriptToEvaluateOnNewDocument', source=HOOK)
   goto_url("https://example.com/page")
   wait_for_load()
   print(page_info())
   print(js('window.__qa_errors || []'))
   ```
   Re-register the hook at the start of any later call that navigates. Silent JS errors are high-value findings.

2. **Read the page structure** — list visible interactive elements with their viewport centres (use `cdp('Accessibility.getFullAXTree')` and filter in Python when you need roles/names):
   ```python
   # List interactive elements
   print(js("""(() => [...document.querySelectorAll('a,button,input,select,textarea,[role=button]')]
     .filter(e => e.offsetParent).slice(0, 80).map((e, i) => { const r = e.getBoundingClientRect();
       return {i, tag: e.tagName, text: (e.innerText || e.value || e.getAttribute('aria-label') || '').trim().slice(0, 60),
               id: e.id, name: e.name, x: Math.round(r.x + r.width / 2), y: Math.round(r.y + r.height / 2)}; }))()"""))
   ```

3. **Visually assess the page:** call `capture_screenshot()` and inspect the attached image for layout issues, broken elements, or accessibility concerns. If your model cannot view images, pass the printed path to `vision_analyze`.

4. **Test interactive elements** systematically:
   - Click buttons and links: `js("document.querySelector('#submit').click()")`, or `click_at_xy(x, y)` with a centre from step 2
   - Fill forms: `fill_input('input[name=email]', 'test input')`
   - Test keyboard navigation: `cdp('Input.dispatchKeyEvent', type='keyDown', key='Tab', code='Tab', windowsVirtualKeyCode=9)` followed by the matching `keyUp`, then `js('document.activeElement.outerHTML.slice(0, 200)')` to see where focus landed; same pattern with `key='Enter'`, `code='Enter'`, `windowsVirtualKeyCode=13`
   - Scroll through content: `js('window.scrollBy(0, 800)')`
   - Go back: `js('history.back()')`, then `wait_for_load()`
   - Test form validation with invalid inputs
   - Test empty submissions

5. **After each interaction**, in the same call, check for:
   - Console errors: `print(js('window.__qa_errors || []'))`
   - Visual changes: `capture_screenshot()` and compare with the previous one
   - Expected vs actual behavior (`page_info()`, or `js()` reading the relevant element)

### Phase 3: Collect Evidence

For every issue found:

1. **Take a screenshot** showing the issue: `capture_screenshot()` prints the saved path. Copy it to `{output_dir}/screenshots/` under a descriptive name (e.g. `issue-03-broken-login.png`) — you will reference it in the report.

2. **Record the details**:
   - URL where the issue occurs
   - Steps to reproduce
   - Expected behavior
   - Actual behavior
   - Console errors (if any)
   - Screenshot path

3. **Classify the issue** using the issue taxonomy (see `references/issue-taxonomy.md`):
   - Severity: Critical / High / Medium / Low
   - Category: Functional / Visual / Accessibility / Console / UX / Content

### Phase 4: Categorize

1. Review all collected issues.
2. De-duplicate — merge issues that are the same bug manifesting in different places.
3. Assign final severity and category to each issue.
4. Sort by severity (Critical first, then High, Medium, Low).
5. Count issues by severity and category for the executive summary.

### Phase 5: Report

Generate the final report using the template at `templates/dogfood-report-template.md`.

The report must include:
1. **Executive 

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit b421178

Download folder ↗
git clone https://github.com/nousresearch/hermes-agent
git -C hermes-agent checkout b42117873683

The author documents no install command, so this uses the repository directly. Our verdict covers commit b42117873683 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source b42117873683

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/nousresearch/dogfood/badge.svg)](https://modelsatlas.com/skills/nousresearch/dogfood/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/nousresearch/dogfood/badge.svg)](https://modelsatlas.com/skills/nousresearch/dogfood/)

Questions about dogfood

What does the dogfood skill do?
The agent that grows with you
Is dogfood safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can dogfood access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (b42117873683), read on 2026-11-14. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.